Go Back
Choose this branch
Choose this branch
meritocratic
regular
democratic
hot
top
alive
95 posts
Interpretability (ML & AI)
AI Success Models
Lottery Ticket Hypothesis
Conservatism (AI)
Market making (AI safety technique)
Verification
28 posts
Myopia
Self Fulfilling/Refuting Prophecies
Luck
230
A Mechanistic Interpretability Analysis of Grokking
Neel Nanda
4mo
39
172
The Plan - 2022 Update
johnswentworth
19d
33
158
MIRI comments on Cotra's "Case for Aligning Narrowly Superhuman Models"
Rob Bensinger
1y
13
149
A transparency and interpretability tech tree
evhub
6mo
10
138
Opinions on Interpretable Machine Learning and 70 Summaries of Recent Papers
lifelonglearner
1y
16
130
Deep Learning Systems Are Not Less Interpretable Than Logic/Probability/Etc
johnswentworth
6mo
52
111
Conversation with Eliezer: What do you want the system to do?
Akash
5mo
38
108
The case for becoming a black-box investigator of language models
Buck
7mo
19
106
Understanding “Deep Double Descent”
evhub
3y
51
106
How "Discovering Latent Knowledge in Language Models Without Supervision" Fits Into a Broader Alignment Scheme
Collin
5d
18
97
Search versus design
Alex Flint
2y
41
97
Gradations of Inner Alignment Obstacles
abramdemski
1y
22
83
The Singular Value Decompositions of Transformer Weight Matrices are Highly Interpretable
beren
22d
27
81
A positive case for how we might succeed at prosaic AI alignment
evhub
1y
47
174
Self-fulfilling correlations
PhilGoetz
12y
50
103
The Credit Assignment Problem
abramdemski
3y
40
65
Arguments against myopic training
Richard_Ngo
2y
39
63
Why GPT wants to mesa-optimize & how we might change this
John_Maxwell
2y
32
60
Partial Agency
abramdemski
3y
18
55
Fifty Shades of Self-Fulfilling Prophecy
PhilGoetz
8y
87
54
Open Problems with Myopia
Mark Xu
1y
16
54
AI safety via market making
evhub
2y
45
48
Bayesian Evolving-to-Extinction
abramdemski
2y
13
47
LCDT, A Myopic Decision Theory
adamShimi
1y
51
45
An example of self-fulfilling spurious proofs in UDT
cousin_it
10y
43
42
Towards a mechanistic understanding of corrigibility
evhub
3y
26
40
Steering Behaviour: Testing for (Non-)Myopia in Language Models
Evan R. Murphy
15d
16
38
Acceptability Verification: A Research Agenda
David Udell
5mo
0